[gt-user] Re: Deployment topology
Hi Charles, I am trying to install Pegasus with Globus 4.2.0 and Condor 7.0.1. Apparently Pegasus submits a job via port 2119, I think that it is the gatekeeper (GRAM2). Since GT 4.2.0 contains GRAM2, I have configured the gatekeeper and jobmanager as your instructions: GT 4.2.0 GRAM2: Admin Guide: http://www.globus.org/toolkit/docs/4.2/4.2.0/execution/gram2/admin/index.html Although it uses grid-proxy-init, I think that myproxy should also work. (I have also installed certs etc. for grid-proxy-init as the instructions told me). However, the test described in the instructions (http://www.globus.org/toolkit/docs/4.2/4.2.0/execution/gram2/admin/gram2-admin-testing.html ) fails with: -- $ globus-job-run grid2.ramscommunity.org:42762:/O=Grid/OU=GlobusTest/ OU=simpleCA-grid2.ramscommunity.org/OU=ramscommunity.org/CN=Yoichi Takayama /bin/date Mon Oct 6 23:00:16 EST 2008 GRAM Job submission failed because data transfer to the server failed (error code 10) -- Since the normal log file for gatekeeper (var/globus-gatekeeper.log) does not seem to record the globus-personal-gatekeeper, I cannot tell more than this. My steps are described at: http://wiki.ramp.org.au/display/vmware/4.9+Globus+-+Node+2+-+GRAM2+(gsigatekeeper%2C+jobmanager) Can you think of some possible causes for this? Your help would be greatly appreciated. Regards, Yoichi -- Yoichi Takayama, PhD Senior Research Fellow RAMP Project MELCOE (Macquarie E-Learning Centre of Excellence) MACQUARIE UNIVERSITY Phone: +61 (0)2 9850 9073 Fax: +61 (0)2 9850 6527 www.mq.edu.au www.melcoe.mq.edu.au/projects/RAMP/ -- MACQUARIE UNIVERSITY: CRICOS Provider No 2J This message is intended for the addressee named and may contain confidential information. If you are not the intended recipient, please delete it and notify the sender. Views expressed in this message are those of the individual sender, and are not necessarily the views of Macquarie E-Learning Centre Of Excellence (MELCOE) or Macquarie University. smime.p7s Description: S/MIME cryptographic signature
[gt-user] Re: Deployment topology
Googling for that error string returns a copy of the old GT2 GRAM error FAQ: http://drupal.star.bnl.gov/STAR/?q=node/424#transfer Try following the advice in that entry. Charles On Oct 6, 2008, at 7:49 AM, Yoichi Takayama wrote: Hi Charles, I am trying to install Pegasus with Globus 4.2.0 and Condor 7.0.1. Apparently Pegasus submits a job via port 2119, I think that it is the gatekeeper (GRAM2). Since GT 4.2.0 contains GRAM2, I have configured the gatekeeper and jobmanager as your instructions: GT 4.2.0 GRAM2: Admin Guide: http://www.globus.org/toolkit/docs/4.2/4.2.0/execution/gram2/admin/index.html Although it uses grid-proxy-init, I think that myproxy should also work. (I have also installed certs etc. for grid-proxy-init as the instructions told me). However, the test described in the instructions (http://www.globus.org/toolkit/docs/4.2/4.2.0/execution/gram2/admin/gram2-admin-testing.html ) fails with: -- $ globus-job-run grid2.ramscommunity.org:42762:/O=Grid/ OU=GlobusTest/OU=simpleCA-grid2.ramscommunity.org/ OU=ramscommunity.org/CN=Yoichi Takayama /bin/date Mon Oct 6 23:00:16 EST 2008 GRAM Job submission failed because data transfer to the server failed (error code 10) -- Since the normal log file for gatekeeper (var/globus-gatekeeper.log) does not seem to record the globus-personal-gatekeeper, I cannot tell more than this. My steps are described at: http://wiki.ramp.org.au/display/vmware/4.9+Globus+-+Node+2+-+GRAM2+(gsigatekeeper%2C+jobmanager) Can you think of some possible causes for this? Your help would be greatly appreciated. Regards, Yoichi -- Yoichi Takayama, PhD Senior Research Fellow RAMP Project MELCOE (Macquarie E-Learning Centre of Excellence) MACQUARIE UNIVERSITY Phone: +61 (0)2 9850 9073 Fax: +61 (0)2 9850 6527 www.mq.edu.au www.melcoe.mq.edu.au/projects/RAMP/ -- MACQUARIE UNIVERSITY: CRICOS Provider No 2J This message is intended for the addressee named and may contain confidential information. If you are not the intended recipient, please delete it and notify the sender. Views expressed in this message are those of the individual sender, and are not necessarily the views of Macquarie E-Learning Centre Of Excellence (MELCOE) or Macquarie University.
[gt-user] Re: Deployment topology
Hi Thanks for the reply, but this is the test (personal-gatekeeper) and as I said it does not leave any log entry in the real log: $GLOBUS_LOCATION/var/globus-gatekeeper.log. No new entry is there around the time the error occurred. (I will check earlier error - maybe at the start up time errors). - $ myproxy-logon -s grid2 (or grid-prpxy-init) $ globus-personal-gatekeeper -start GRAM contact: grid2.ramscommunity.org:37335:/O=Grid/OU=GlobusTest/ OU=simpleCA-grid2.ramscommunity.org/OU=ramscommunity.org/CN=Yoichi Takayama $ globus-job-run grid2.ramscommunity.org:37335:/O=Grid/OU=GlobusTest/ OU=simpleCA-grid2.ramscommunity.org/OU=ramscommunity.org/CN=Yoichi Takayama /bin/date GRAM Job submission failed because data transfer to the server failed (error code 10) (just trying single quote for the user QN in case) $ globus-job-run grid2.ramscommunity.org:37335:'/O=Grid/OU=GlobusTest/ OU=simpleCA-grid2.ramscommunity.org/OU=ramscommunity.org/CN=Yoichi Takayama' /bin/date GRAM Job submission failed because the connection to the server failed (check host and port) (error code 12) $ globus-personal-gatekeeper -killall killing gatekeeper: grid2.ramscommunity.org:37335:/O=Grid/ OU=GlobusTest/OU=simpleCA-grid2.ramscommunity.org/OU=ramscommunity.org/ CN=Yoichi Takayama - The entry seems to be correct in the /etc/grid-security/grid-mapfile - # cat /etc/grid-security/grid-mapfile /O=Grid/OU=GlobusTest/OU=simpleCA-grid2.ramscommunity.org/ OU=ramscommunity.org/CN=Yoichi Takayama yoichi - Also, $GLOBUS_LOCATION/etc/globus-gatekeeper.conf seems OK - # cat $GLOBUS_LOCATION/etc/globus-gatekeeper.conf -x509_cert_dir /etc/grid-security/certificates -x509_user_cert /etc/grid-security/hostcert.pem -x509_user_key /etc/grid-security/hostkey.pem -gridmap /etc/grid-security/grid-mapfile -home /usr/local/globus -e libexec -logfile var/globus-gatekeeper.log -port 2119 -grid_services etc/grid-services -xinetd -seg - xintet.d for the gatekeeper is set up. - # cat /etc/xinetd.d/globus-gatekeeper service gsigatekeeper { socket_type = stream protocol = tcp wait = no user = root env = LD_LIBRARY_PATH=/usr/local/globus/lib server = /usr/local/globus/sbin/globus-gatekeeper server_args = -conf /usr/local/globus/etc/globus-gatekeeper.conf disable = no } - Port 2119 is in the /etc/services and it is LISTENning. Thanks, Yoichi -- Yoichi Takayama, PhD Senior Research Fellow RAMP Project MELCOE (Macquarie E-Learning Centre of Excellence) MACQUARIE UNIVERSITY Phone: +61 (0)2 9850 9073 Fax: +61 (0)2 9850 6527 www.mq.edu.au www.melcoe.mq.edu.au/projects/RAMP/ -- MACQUARIE UNIVERSITY: CRICOS Provider No 2J This message is intended for the addressee named and may contain confidential information. If you are not the intended recipient, please delete it and notify the sender. Views expressed in this message are those of the individual sender, and are not necessarily the views of Macquarie E-Learning Centre Of Excellence (MELCOE) or Macquarie University. On 07/10/2008, at 12:33 AM, Charles Bacon wrote: Googling for that error string returns a copy of the old GT2 GRAM error FAQ: http://drupal.star.bnl.gov/STAR/?q=node/424#transfer Try following the advice in that entry. Charles On Oct 6, 2008, at 7:49 AM, Yoichi Takayama wrote: Hi Charles, I am trying to install Pegasus with Globus 4.2.0 and Condor 7.0.1. Apparently Pegasus submits a job via port 2119, I think that it is the gatekeeper (GRAM2). Since GT 4.2.0 contains GRAM2, I have configured the gatekeeper and jobmanager as your instructions: GT 4.2.0 GRAM2: Admin Guide: http://www.globus.org/toolkit/docs/4.2/4.2.0/execution/gram2/admin/index.html Although it uses grid-proxy-init, I think that myproxy should also work. (I have also installed certs etc. for grid-proxy-init as the instructions told me). However, the test described in the instructions (http://www.globus.org/toolkit/docs/4.2/4.2.0/execution/gram2/admin/gram2-admin-testing.html ) fails with: -- $ globus-job-run grid2.ramscommunity.org:42762:/O=Grid/ OU=GlobusTest/OU=simpleCA-grid2.ramscommunity.org/ OU=ramscommunity.org/CN=Yoichi Takayama /bin/date Mon Oct 6 23:00:16 EST 2008 GRAM Job submission
[gt-user] Re: Deployment topology
Hi Charles, Great! That may give more clue as to what may be wrong. --- $ grid-proxy-init -debug -verify User Cert File: /home/yoichi/.globus/usercert.pem User Key File: /home/yoichi/.globus/userkey.pem Trusted CA Cert Dir: /etc/grid-security/certificates Output File: /tmp/x509up_u500 Your identity: /O=Grid/OU=GlobusTest/OU=simpleCA- grid2.ramscommunity.org/OU=ramscommunity.org/CN=Yoichi Takayama Enter GRID pass phrase for this identity: Creating proxy ... Done Proxy Verify OK Your proxy is valid until: Tue Oct 7 13:51:50 2008 $ globus-personal-gatekeeper -start GRAM contact: grid2.ramscommunity.org:44306:/O=Grid/OU=GlobusTest/ OU=simpleCA-grid2.ramscommunity.org/OU=ramscommunity.org/CN=Yoichi Takayama $ globus-job-run grid2.ramscommunity.org:44306:/O=Grid/OU=GlobusTest/ OU=simpleCA-grid2.ramscommunity.org/OU=ramscommunity.org/CN=Yoichi Takayama /bin/date GRAM Job submission failed because data transfer to the server failed (error code 10) --- Checking the gridmap file --- $ cd /home/yoichi/.globus/./personal- gatekeeper.grid2.ramscommunity.org.11253 $ ls -l total 48 -rw-rw-r-- 1 yoichi yoichi 314 Oct 7 01:51 gatekeeper.conf -rw-rw-r-- 1 yoichi yoichi 492 Oct 7 01:51 gatekeeper.log -rw-rw-r-- 1 yoichi yoichi 6 Oct 7 01:51 gatekeeper.pid -rw-rw-r-- 1 yoichi yoichi 107 Oct 7 01:51 gridmap -rw-rw-r-- 1 yoichi yoichi 183 Oct 7 01:51 jobmanager -rw-rw-r-- 1 yoichi yoichi 502 Oct 7 01:51 jobmanager.conf $ cat gridmap /O=Grid/OU=GlobusTest/OU=simpleCA-grid2.ramscommunity.org/ OU=ramscommunity.org/CN=Yoichi Takayama yoichi --- H, the log contains this: --- $ cat /home/yoichi/.globus/./personal- gatekeeper.grid2.ramscommunity.org.11253/*log TIME: Tue Oct 7 01:51:54 2008 PID: 11333 -- Notice: 6: /usr/local/globus/sbin/globus-gatekeeper pid=11333 starting at Tue Oct 7 01:51:54 2008 TIME: Tue Oct 7 01:51:54 2008 PID: 11334 -- Notice: 6: /usr/local/globus/sbin/globus-gatekeeper pid=11334 starting at Tue Oct 7 01:51:54 2008 TIME: Tue Oct 7 01:51:54 2008 PID: 11334 -- Notice: 6: GRAM contact: grid2.ramscommunity.org: 44306:/O=Grid/OU=GlobusTest/OU=simpleCA-grid2.ramscommunity.org/ OU=ramscommunity.org/CN=Yoichi Takayama TIME: Tue Oct 7 01:55:04 2008 PID: 11460 -- Notice: 6: Got connection 137.111.246.176 at Tue Oct 7 01:55:04 2008 TIME: Tue Oct 7 01:55:04 2008 PID: 11460 -- Notice: 5: Authenticated globus user: /O=Grid/ OU=GlobusTest/OU=simpleCA-grid2.ramscommunity.org/OU=ramscommunity.org/ CN=Yoichi Takayama TIME: Tue Oct 7 01:55:04 2008 PID: 11460 -- Notice: 0: GRID_SECURITY_HTTP_BODY_FD=7 TIME: Tue Oct 7 01:55:04 2008 PID: 11460 -- Notice: 5: Requested service: jobmanager TIME: Tue Oct 7 01:55:04 2008 PID: 11460 -- Notice: 5: Authorized as local user: yoichi TIME: Tue Oct 7 01:55:04 2008 PID: 11460 -- Notice: 5: Authorized as local uid: 500 TIME: Tue Oct 7 01:55:04 2008 PID: 11460 -- Notice: 5: and local gid: 500 TIME: Tue Oct 7 01:55:04 2008 PID: 11460 -- Notice: 0: executing /usr/local/globus/libexec/globus- job-manager --- It seems that the authentication tool place OK, despite what the other web page implied that the entry may not be in the gridmap file. Although it says that it was executing the job-manager, does this mean the job submission failed??? Or, does that GRID_SECURITY_HTTP_BODY_FD=7 mean that the request failed??? I don't think I ever got the /bin/date results back. Thanks, Yoichi -- Yoichi Takayama, PhD Senior Research Fellow RAMP Project MELCOE (Macquarie E-Learning Centre of Excellence) MACQUARIE UNIVERSITY Phone: +61 (0)2 9850 9073 Fax: +61 (0)2 9850 6527 www.mq.edu.au www.melcoe.mq.edu.au/projects/RAMP/ -- MACQUARIE UNIVERSITY: CRICOS Provider No 2J This message is intended for the addressee named and may contain confidential information. If you are not the intended recipient, please delete it and notify the sender. Views expressed in this message are those of the individual sender, and are not necessarily the views of Macquarie E-Learning Centre Of Excellence (MELCOE) or Macquarie University. On 07/10/2008, at 1:49 AM, Charles Bacon wrote:
Re: [gt-user] Re: Deployment topology
I thought that it was your own manual! http://www.globus.org/toolkit/docs/4.2/4.2.0/execution/gram2/admin/gram2-admin-configuring.html#gram2-admin-starting This page states both as options and I have copied the /etc/xinetd.d/ globus-gatekeeper example from it. i.e. 2. Configure Inetd and Xinetd While running globus-personal-gatekeeper as a user is a good test, you will want to configure your machine to run globus-gatekeeper as root, so that other people will be able to use your gatekeeper. If you just run the personal gatekeeper, you won't have authority to su to other user accounts. To setup a full gatekeeper, you will need to make the following modifications as root: In /etc/services, add the service name gsigatekeeper to port 2119. gsigatekeeper 2119/tcp # Globus Gatekeeper Depending on whether your host is running inetd or xinetd, you will need to modify its configuration. If the directory /etc/xinetd.d/ exists, then your host is likely running xinetd. If the directory doesn't exist, your host is likely running inetd. Follow the appropriate instructions below according to what your host is running. etc. etc. Xinetd For xinetd, add a file called globus-gatekeeper to the /etc/ xinetd.d/ directory that has the following contents. Be sure to replace GLOBUS_LOCATION below with the actual value of $GLOBUS_LOCATION in your environment. service gsigatekeeper { socket_type = stream protocol = tcp wait = no user = root env = LD_LIBRARY_PATH=GLOBUS_LOCATION/lib server = GLOBUS_LOCATION/sbin/globus-gatekeeper server_args = -conf GLOBUS_LOCATION/etc/globus-gatekeeper.conf disable = no } In general, I am running xinetd than inetd. for GridFTP and MyProxy: # ls -l /etc/xinetd.d total 168 -rw-r--r-- 1 root root 333 Oct 5 00:48 globus-gatekeeper -rw-r--r-- 1 root root 495 Sep 30 21:19 gridftp -rw-r--r-- 1 root root 326 Sep 9 2004 gssftp -rw-r--r-- 1 root root 310 Sep 9 2004 klogin ... -rw-r--r-- 1 root root 279 Sep 24 08:56 myproxy ... Although it does not seem to be wrong to be using xinetd, should I also install inetd??? Thanks, Yoichi -- Yoichi Takayama, PhD Senior Research Fellow RAMP Project MELCOE (Macquarie E-Learning Centre of Excellence) MACQUARIE UNIVERSITY Phone: +61 (0)2 9850 9073 Fax: +61 (0)2 9850 6527 www.mq.edu.au www.melcoe.mq.edu.au/projects/RAMP/ -- MACQUARIE UNIVERSITY: CRICOS Provider No 2J This message is intended for the addressee named and may contain confidential information. If you are not the intended recipient, please delete it and notify the sender. Views expressed in this message are those of the individual sender, and are not necessarily the views of Macquarie E-Learning Centre Of Excellence (MELCOE) or Macquarie University. On 07/10/2008, at 6:45 AM, Charles Bacon wrote: xinetd does not appear to be a legal option; what document instructed you to use that? I believe it should just be -inetd. Charles On Oct 6, 2008, at 10:45 AM, Yoichi Takayama wrote: Trying the real gatekeeper 2119(tcp): $ globus-job-run grid2.ramscommunity.org:2119:/O=Grid/ OU=GlobusTest/OU=simpleCA-grid2.ramscommunity.org/ OU=ramscommunity.org/CN=Yoichi Takayama /bin/date GRAM Job submission failed because the connection to the server failed (check host and port) (error code 12) Trying the real gatekeeper 2119(tcp) with telnet: $ telnet -l '/O=Grid/OU=GlobusTest/OU=simpleCA- grid2.ramscommunity.org/OU=ramscommunity.org/CN=Yoichi Takayama' grid2.ramscommunity.org 2119 Trying 137.111.246.176... Connected to grid2.ramscommunity.org (137.111.246.176). Escape character is '^]'. Unknown argument -xinetd Usage: globus-gatekeeper {-conf parmfile [-test]} | {[-d[ebug] [- inetd | -f] [-p[ort] port] [-home path] [-l[ogfile] logfile] [-e path] [-grid_services file] [-globusid globusid] [-gridmap file] [-globuspwd file] [-x509_cert_dir path] [-x509_cert_file file] [- x509_user_cert file] [-x509_user_key file] [-x509_user_proxy file] [-k] [-globuskmap file] [-test]} Connection closed by foreign host. Yoichi -- Yoichi Takayama, PhD Senior Research Fellow RAMP Project MELCOE (Macquarie E-Learning Centre of Excellence) MACQUARIE UNIVERSITY Phone: +61 (0)2 9850 9073 Fax: +61 (0)2 9850 6527 www.mq.edu.au www.melcoe.mq.edu.au/projects/RAMP/ -- MACQUARIE UNIVERSITY: CRICOS Provider No 2J This message is intended for the addressee named and may contain confidential information. If you are not the intended recipient, please delete it and notify the sender. Views expressed in this message are those of the individual sender, and are not
Re: [gt-user] Re: Deployment topology
Oh! Just I want to clarify. So, I leave it as inetd, although I can still use the xinetd? Or, should I take it out? Or, are you saying that I should switch to inetd? Great, and thanks! Yoichi -- Yoichi Takayama, PhD Senior Research Fellow RAMP Project MELCOE (Macquarie E-Learning Centre of Excellence) MACQUARIE UNIVERSITY Phone: +61 (0)2 9850 9073 Fax: +61 (0)2 9850 6527 www.mq.edu.au www.melcoe.mq.edu.au/projects/RAMP/ -- MACQUARIE UNIVERSITY: CRICOS Provider No 2J This message is intended for the addressee named and may contain confidential information. If you are not the intended recipient, please delete it and notify the sender. Views expressed in this message are those of the individual sender, and are not necessarily the views of Macquarie E-Learning Centre Of Excellence (MELCOE) or Macquarie University. On 07/10/2008, at 11:55 AM, Charles Bacon wrote: Using xinetd to start the gatekeeper is fine; nothing in that page tells you to put -xinetd in the globus-gatekeeper.conf. Valid settings are either -inetd or nothing. You want -inetd. Charles On Oct 6, 2008, at 7:40 PM, Yoichi Takayama wrote: I thought that it was your own manual! http://www.globus.org/toolkit/docs/4.2/4.2.0/execution/gram2/admin/gram2-admin-configuring.html#gram2-admin-starting This page states both as options and I have copied the /etc/ xinetd.d/globus-gatekeeper example from it. i.e. 2. Configure Inetd and Xinetd While running globus-personal-gatekeeper as a user is a good test, you will want to configure your machine to run globus-gatekeeper as root, so that other people will be able to use your gatekeeper. If you just run the personal gatekeeper, you won't have authority to su to other user accounts. To setup a full gatekeeper, you will need to make the following modifications as root: In /etc/services, add the service name gsigatekeeper to port 2119. gsigatekeeper 2119/tcp # Globus Gatekeeper Depending on whether your host is running inetd or xinetd, you will need to modify its configuration. If the directory /etc/xinetd.d/ exists, then your host is likely running xinetd. If the directory doesn't exist, your host is likely running inetd. Follow the appropriate instructions below according to what your host is running. etc. etc. Xinetd For xinetd, add a file called globus-gatekeeper to the /etc/ xinetd.d/ directory that has the following contents. Be sure to replace GLOBUS_LOCATION below with the actual value of $GLOBUS_LOCATION in your environment. service gsigatekeeper { socket_type = stream protocol = tcp wait = no user = root env = LD_LIBRARY_PATH=GLOBUS_LOCATION/lib server = GLOBUS_LOCATION/sbin/globus-gatekeeper server_args = -conf GLOBUS_LOCATION/etc/globus-gatekeeper.conf disable = no } In general, I am running xinetd than inetd. for GridFTP and MyProxy: # ls -l /etc/xinetd.d total 168 -rw-r--r-- 1 root root 333 Oct 5 00:48 globus-gatekeeper -rw-r--r-- 1 root root 495 Sep 30 21:19 gridftp -rw-r--r-- 1 root root 326 Sep 9 2004 gssftp -rw-r--r-- 1 root root 310 Sep 9 2004 klogin ... -rw-r--r-- 1 root root 279 Sep 24 08:56 myproxy ... Although it does not seem to be wrong to be using xinetd, should I also install inetd??? Thanks, Yoichi -- Yoichi Takayama, PhD Senior Research Fellow RAMP Project MELCOE (Macquarie E-Learning Centre of Excellence) MACQUARIE UNIVERSITY Phone: +61 (0)2 9850 9073 Fax: +61 (0)2 9850 6527 www.mq.edu.au www.melcoe.mq.edu.au/projects/RAMP/ -- MACQUARIE UNIVERSITY: CRICOS Provider No 2J This message is intended for the addressee named and may contain confidential information. If you are not the intended recipient, please delete it and notify the sender. Views expressed in this message are those of the individual sender, and are not necessarily the views of Macquarie E-Learning Centre Of Excellence (MELCOE) or Macquarie University. On 07/10/2008, at 6:45 AM, Charles Bacon wrote: xinetd does not appear to be a legal option; what document instructed you to use that? I believe it should just be -inetd. Charles On Oct 6, 2008, at 10:45 AM, Yoichi Takayama wrote: Trying the real gatekeeper 2119(tcp): $ globus-job-run grid2.ramscommunity.org:2119:/O=Grid/ OU=GlobusTest/OU=simpleCA-grid2.ramscommunity.org/ OU=ramscommunity.org/CN=Yoichi Takayama /bin/date GRAM Job submission failed because the connection to the server failed (check host and port) (error code 12) Trying the real gatekeeper 2119(tcp) with telnet: $ telnet -l '/O=Grid/OU=GlobusTest/OU=simpleCA- grid2.ramscommunity.org/OU=ramscommunity.org/CN=Yoichi
[gt-user] Re: Deployment topology
Here's a little cleanup of the confusion: Condor-G is a job submission client. Condor is a resource manager. GRAM is an abstract interface to resource managers. So using Condor-G to submit to GRAM that runs jobs on Condor is not as silly as it might sound. I think maybe you are trying to solve this all in your head before you start working with it; I'm not sure that's going to work. It sounds like what you want is: A condor pool. A machine running GRAM that can run condor_submit to your condor pool. A client that runs Pegasus+Condor-G. Then you can use your client to submit a job to your GRAM host and see if that's enough. If it's not, it sounds like what you need additionally is an installation of Globus that is shared by your condor pool nodes, but that they don't need to be running services; they just need access to your clients. Charles On Oct 1, 2008, at 11:40 PM, Yoichi Takayama wrote: Hi I need your advice. Neither Condor or Globus manual is too clear about the deployment topology that works. The figures below are the only references I can get and I am guessing. If I am configuring a local Condor pool managed by Globus which can run Pegasus (DAG generator for Globus), do I need something like below??? 1. Condor Submit machines with Pegasus, Condor-G and Condor Submit daemon installed. (There may be several of these, which are a part of the local Condor cluster, i.e. share the same pool name. They may create local or remote jobs.) Does these machines need to have Globus installed or instructed as to where the Globus manager is? I have not encountered how to configure Condor-G to know that. If a job using gt4 universe is sent to local Condor (Submit daemon), does it automatically know to call Globus, if the setup-globus-gram-job- manager has been run by globus on that node? Or, does the job sent to the central manager(s) first and do they work it our there then? Only the managers need to know the association??? For the local cluster: 2. A Globus Manager machine with Globus services (GRAM, RFT, GridFTP), configured to use Condor as the job-manager. (Pegasus submits a job to Condor-G that will use Globus to manage the job but uses Condor to run??) 3. A Condor Manager machine which Globus is configured to use. (This could be the Globus Manger machine). 4. A Condor cluster with Execute nodes (may mount NFS to share executables and data needed for the jobs??) - no GridFTP (If a Globus job is to run on a remote site, the site also needs to have GridFTP installed.) Thanks, Yoichi - This figure is from GT4 Primer: GRAM in GT4.png - This figure is from Condor 7.0.4 manual (for gt2 job): gt2 Universe job.png -- Yoichi Takayama, PhD Senior Research Fellow RAMP Project MELCOE (Macquarie E-Learning Centre of Excellence) MACQUARIE UNIVERSITY Phone: +61 (0)2 9850 9073 Fax: +61 (0)2 9850 6527 www.mq.edu.au www.melcoe.mq.edu.au/projects/RAMP/ -- MACQUARIE UNIVERSITY: CRICOS Provider No 2J This message is intended for the addressee named and may contain confidential information. If you are not the intended recipient, please delete it and notify the sender. Views expressed in this message are those of the individual sender, and are not necessarily the views of Macquarie E-Learning Centre Of Excellence (MELCOE) or Macquarie University. On 02/10/2008, at 12:12 AM, Charles Bacon wrote: Not really, no. The idea is that you run some kind of local scheduler (like, say, Condor) and just use a single Globus node to address those instances. If you need access to the client binaries, you can mount them on NFS. But there's not much reason for a single resource pool to need more than one GRAM, RFT, or Index service to talk to it. Charles